mlsanityData to 7 Oct 2026

Learned Image Compression with Mixed Transformer-CNN Architectures

arXiv 2303.14978 ↗First posted 27 Mar 2023eess.IV cs.CVcited by 205

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Learned image compression (LIC) methods have exhibited promising progress and superior rate-distortion performance compared with classical image compression standards. Most existing LIC methods are Convolutional Neural Networks-based (CNN-based) or Transformer-based, which have different advantages. Exploiting both advantages is a point worth exploring, which has two challenges: 1) how to effectively fuse the two methods? 2) how to achieve higher performance with a suitable complexity? In this paper, we propose an efficient parallel Transformer-CNN Mixture (TCM) block with a controllable complexity to incorporate the local modeling ability of CNN and the non-local modeling ability of transformers to improve the overall architecture of image compression models. Besides, inspired by the recent progress of entropy estimation models and attention modules, we propose a channel-wise entropy model with parameter-efficient swin-transformer-based attention (SWAtten) modules by using channel squeezing. Experimental results demonstrate our proposed method achieves state-of-the-art rate-distortion performances on three different resolution datasets (i.e., Kodak, Tecnick, CLIC Professional Validation) compared to existing LIC methods. The code is at https://github.com/jmliu206/LIC_TCM.

Key facts. Cited by 205 papers in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

25 of 39 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2018Variational image compression with a scale hyperpriorcited by 910
  7. 2016End-to-end Optimized Image Compressioncited by 673
  8. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  9. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  10. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  11. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  12. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
13 more
  1. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  2. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  3. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  4. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  5. 2020Causal Contextual Prediction for Learned Image Compressioncited by 70
  6. 2021Transformer-based Image Compressioncited by 60
  7. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
  8. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  9. 2021Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modulescited by 33
  10. 2020Learned Block-based Hybrid Image Compressioncited by 30
  11. 2022Neural Data-Dependent Transform for Learned Image Compressioncited by 29
  12. 2022Memory-Efficient Learned Image Compression with Pruned Hyperprior Modulecited by 6
  13. 2023Multistage Spatial Context Models for Learned Image Compressioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 70; 2025: 77; 2026: 45.

205 papers.

Sort:

By area:

  1. 2024Neural Video Compression with Feature Modulationcited by 115
  2. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 97
  3. 2025Towards Practical Real-Time Neural Video Compressioncited by 72
  4. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  5. 2023Frequency-Aware Transformer for Learned Image Compressioncited by 56
  6. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  7. 2025Learned Image Compression with Dictionary-based Entropy Modelcited by 29
  8. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  9. 2024MambaVC: Learned Visual Compression with Selective State Spacescited by 28
  10. 2024Idempotence and Perceptual Image Compressioncited by 27
  11. 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
  12. 2023Compression with Bayesian Implicit Neural Representationscited by 25
38 more
  1. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  2. 2024CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformercited by 22
  3. 2025Linear Attention Modeling for Learned Image Compressioncited by 22
  4. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
  5. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  6. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  7. 2024Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelitycited by 20
  8. 2025DLF: Extreme Image Compression with Dual-generative Latent Fusioncited by 20
  9. 2025Learned Image Compression with Hierarchical Progressive Context Modelingcited by 20
  10. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  11. 2025MambaIC: State Space Models for High-Performance Learned Image Compressioncited by 18
  12. 2024Image Coding for Machines with Edge Information Learning Using Segment Anythingcited by 17
  13. 2024NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representationcited by 16
  14. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  15. 2025Large Language Model for Lossless Image Compression with Visual Promptscited by 15
  16. 2025Neural Video Compression with Context Modulationcited by 15
  17. 2024All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregationcited by 14
  18. 2023Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compressioncited by 13
  19. 2024Rate-Distortion-Cognition Controllable Versatile Neural Image Compressioncited by 11
  20. 2025Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compressioncited by 10
  21. 2023RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representationscited by 9
  22. 2024Region-Adaptive Transform with Segmentation Prior for Image Compressioncited by 8
  23. 2024Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Modelcited by 8
  24. 2024Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compressioncited by 8
  25. 2024Generalized Gaussian Model for Learned Image Compressioncited by 8
  26. 2023Image Coding for Machines with Object Region Learningcited by 7
  27. 2024Generalized Nested Latent Variable Models for Lossy Coding applied to Wind Turbine Scenarioscited by 7
  28. 2023LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compressioncited by 6
  29. 2024GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compressioncited by 6
  30. 2024Scalable Image Coding for Humans and Machines Using Feature Fusion Networkcited by 6
  31. 2024Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMscited by 5
  32. 2024DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Codingcited by 5
  33. 2024Attention Based Machine Learning Methods for Data Reduction with Guaranteed Error Boundscited by 5
  34. 2024Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorizationcited by 5
  35. 2025Balanced Rate-Distortion Optimization in Learned Image Compressioncited by 5
  36. 2025Content-Aware Mamba for Learned Image Compressioncited by 5
  37. 2023Neural Image Compression: Generalization, Robustness, and Spectral Biasescited by 4
  38. 2024Refining Coded Image in Human Vision Layer Using CNN-Based Post-Processingcited by 4

50 most cited of 205 All 205 (JSON)